PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-693",
"CWE-78",
"CWE-863"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/56xxx/CVE-2026-56838.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "4.5.87"
},
{
"fixed": "4.6.59"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StringRangeExpression"
},
{
"range": [
{
"introduced": "0"
},
{
"fixed": "4.6.59"
}
],
"source": "DESCRIPTION"
}
]
}